@inproceedings{rani-etal-2022-mhe,
title = "{MHE}: Code-Mixed Corpora for Similar Language Identification",
author = "Rani, Priya and
McCrae, John P. and
Fransen, Theodorus",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.366",
pages = "3425--3433",
abstract = "This paper introduces a new Magahi-Hindi-English (MHE) code-mixed data-set for similar language identification (SMLID), where Magahi is a less-resourced minority language. This corpus provides a language id at two levels: word and sentence. This data-set is the first Magahi-Hindi-English code-mixed data-set for similar language identification task. Furthermore, we will discuss the complexity of the data-set and provide a few baselines for the language identification task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rani-etal-2022-mhe">
<titleInfo>
<title>MHE: Code-Mixed Corpora for Similar Language Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Priya</namePart>
<namePart type="family">Rani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Theodorus</namePart>
<namePart type="family">Fransen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces a new Magahi-Hindi-English (MHE) code-mixed data-set for similar language identification (SMLID), where Magahi is a less-resourced minority language. This corpus provides a language id at two levels: word and sentence. This data-set is the first Magahi-Hindi-English code-mixed data-set for similar language identification task. Furthermore, we will discuss the complexity of the data-set and provide a few baselines for the language identification task.</abstract>
<identifier type="citekey">rani-etal-2022-mhe</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.366</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3425</start>
<end>3433</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MHE: Code-Mixed Corpora for Similar Language Identification
%A Rani, Priya
%A McCrae, John P.
%A Fransen, Theodorus
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F rani-etal-2022-mhe
%X This paper introduces a new Magahi-Hindi-English (MHE) code-mixed data-set for similar language identification (SMLID), where Magahi is a less-resourced minority language. This corpus provides a language id at two levels: word and sentence. This data-set is the first Magahi-Hindi-English code-mixed data-set for similar language identification task. Furthermore, we will discuss the complexity of the data-set and provide a few baselines for the language identification task.
%U https://aclanthology.org/2022.lrec-1.366
%P 3425-3433
Markdown (Informal)
[MHE: Code-Mixed Corpora for Similar Language Identification](https://aclanthology.org/2022.lrec-1.366) (Rani et al., LREC 2022)
ACL